Work

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning

Year: 2024

Type: conference-paper

Abstract: Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2024.emnlp-main.245

Authors: Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu

Institutions: IBM (United States), Lawrence Livermore National Laboratory, Michigan State University, MIT-IBM Computing Research Lab, Massachusetts Institute of Technology

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: CAREER: Zeroth-Order Machine Learning: Foundations and Emerging Applications, Collaborative Research: RI: Small: Advancing Theory and Practice of Trustworthy Machine Learning via Bi-Level Optimization

OpenAlex ID: W4404782927

FWCI: 4.62

Cites:

Cited by: 16

Related to: 10